Production line task scheduling method and device based on resource capability value

Abstract

The invention relates to the technical field of task scheduling, and discloses a production line task scheduling method and device based on a resource capability value, and the method comprises the steps: obtaining a capability value requirement list of a target task and resource features of all resources in task scheduling software; a resource capability model is adopted to carry out capability evaluation based on the resource features, capability values of the resources under multiple capability evaluation dimensions are obtained and stored in a resource database, and the capability values are used for measuring the productivity of the resources under any capability evaluation dimension; screening candidate resources meeting the capability value requirement list from a resource database; determining a target resource based on the historical task and the candidate resource; and allocating the target resource to the target task. According to the method, multi-dimensional capability evaluation is carried out on the resources through the resource capability model, the productivity of the resources is quantified, the target resources are jointly determined with reference to data of historical tasks for task scheduling, the resource utilization rate and the production efficiency are improved, and meanwhile, the method can adapt to complex and changeable production line scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of task scheduling, and in particular to a method and device for scheduling production line tasks based on resource capability values. Background Art

[0002] With the rapid development of information technology and industrial automation, task scheduling has become an important factor affecting the field of modern production. Traditional task scheduling methods treat resources of the same type as undifferentiated units and mainly rely on resource occupancy to allocate tasks. For example, if lathe A is executing a process and lathe B is idle, the existing task scheduling software will assign lathe B to the target task. This will lead to the phenomenon of "resource islands" in which some resources are overused while other resources are idle in the actual production process, which seriously restricts the improvement of production efficiency and resource utilization, and cannot be applied to large-scale, complex and changeable production line scenarios. Summary of the invention

[0003] In view of this, the present invention provides a production line task scheduling method and device based on resource capability value to solve the problem that the existing task scheduling has the "resource island" phenomenon, reduces production efficiency and resource utilization, and cannot be applied to complex and changeable production line scenarios.

[0004] In a first aspect, the present invention provides a production line task scheduling method based on resource capability value, the method comprising:

[0005] Obtain the capability value requirement list of the target task and the resource characteristics of all resources in the task scheduling software;

[0006] For each resource, the resource capability model is used to evaluate the capability of the resource based on its resource characteristics, and the capability value of the resource under multiple capability evaluation dimensions is obtained and stored in the resource database of the task scheduling software. The capability value is used to measure the productivity of the resource under any capability evaluation dimension.

[0007] Screening multiple candidate resources that meet the capability value requirement list of the target task from the resource database;

[0008] Determine target resources based on historical tasks and multiple candidate resources;

[0009] Assign target resources to target tasks.

[0010] The production line task scheduling method based on resource capability values ​​provided in the embodiment of the present invention obtains the capability value requirement list of the target task to understand the requirements of the target task. At the same time, it collects the resource characteristics of all resources in the task scheduling software, which helps to fully grasp the situation of available resources, and uses the resource capability model to perform multi-dimensional capability evaluation on each resource, quantify the productivity of the resources, and provide data support for subsequent task scheduling. By comparing with the requirement list of the target task, it can quickly locate qualified candidate resources, improve task scheduling efficiency, comprehensively determine the target resources based on historical tasks and candidate resources, and schedule the target resources to the target task. Compared with task scheduling based on whether the resources are idle, it improves resource utilization and production efficiency, optimizes resource allocation, and can adapt to complex and changeable production line scenarios.

[0011] In an optional embodiment, the resource characteristics include test data and historical performance data;

[0012] For each resource, the resource capability model is used to evaluate the capability based on the resource characteristics, and the capability value of the resource under multiple capability evaluation dimensions is obtained, including:

[0013] Based on the test data and historical performance data in the resource characteristics of each resource, all resources are divided into known resources and unknown resources;

[0014] For any known resource, based on the resource characteristics of the known resource, the empirical formula in the resource capability model is used to determine the capability value of the known resource in multiple capability assessment dimensions;

[0015] For any unknown resource, the graph clustering model in the resource capability model is used to obtain the capability value of the unknown resource in each capability assessment dimension. The graph clustering model is trained based on known resources.

[0016] The production line task scheduling method based on resource capability values ​​provided in an embodiment of the present invention can adopt differentiated capability value determination methods for different types of resources by dividing known resources and unknown resources based on test data and historical performance data, thereby improving the efficiency and accuracy of capability assessment.

[0017] In an optional implementation, for any known resource, based on the resource characteristics of the known resource, an empirical formula in the resource capability model is used to determine the capability value of the known resource in multiple capability evaluation dimensions, including:

[0018] For any capability assessment dimension, based on the resource characteristics of known resources, determine the actual production capacity and test yield rate of the known resources in the capability assessment dimension;

[0019] Obtaining the health index, resource utilization, and resource penalty value of known resources, where the resource penalty value is used to reduce the scheduling of known resources when the resource utilization of the known resources exceeds a preset threshold;

[0020] An empirical formula is used to determine the capacity value of known resources in the capacity assessment dimension based on their actual production capacity, test yield, health index, resource utilization rate, and resource penalty value in the capacity assessment dimension.

[0021] The production line task scheduling method based on resource capability value provided by the embodiment of the present invention obtains multiple data of known resources, comprehensively considers multiple key indicators such as actual production capacity, test yield, health index, resource utilization and resource penalty value, and forms a comprehensive capability evaluation system, which can more accurately describe the productivity of resources.

[0022] In an optional implementation, for any unknown resource, a graph clustering model in a resource capability model is used to obtain the capability value of the unknown resource in each capability evaluation dimension, including:

[0023] Based on the resource characteristics of the unknown resource, the similarity between the unknown resource and each cluster in the graph clustering model is calculated;

[0024] Based on the capability values ​​of all known resources in the cluster with the largest similarity in multiple capability evaluation dimensions, the capability values ​​of unknown resources in multiple capability evaluation dimensions are determined.

[0025] The production line task scheduling method based on resource capability value provided by the embodiment of the present invention can allocate unknown resources to the most similar clustering clusters by calculating the similarity between unknown resources and each clustering cluster, so as to find a suitable reference object for it, and then determine the capability value of the unknown resource based on the known resources, thereby improving the reliability and rationality of the unknown resource capability evaluation and reducing the evaluation error caused by the lack of direct empirical data.

[0026] In an optional implementation, obtaining a capability value requirement list for a target task includes:

[0027] Based on the target tasks, multiple task requirement dimensions are divided;

[0028] Determine the capability value corresponding to each task requirement dimension;

[0029] Based on the non-capability value conditions of the target task, all task requirement dimensions and the capability value corresponding to each task requirement dimension, a capability value requirement list for the target task is generated.

[0030] The production line task scheduling method based on resource capability value provided by the embodiment of the present invention subdivides the target task into multiple independent task requirement dimensions, thereby quantitatively evaluating each task requirement dimension and obtaining the corresponding capability value. Meanwhile, other non-capability value conditions are considered to generate a complete capability value requirement list, thereby providing data support for task scheduling.

[0031] In an optional implementation, multiple candidate resources that meet the capability value requirement list of the target task are screened from the resource database, including:

[0032] Based on multiple task requirement dimensions in the capability value requirement list of the target task, multiple intermediate resources are screened from the resource database;

[0033] Based on the non-capability value conditions in the capability value requirement list, a plurality of candidate resources are determined from the plurality of intermediate resources.

[0034] The method for scheduling production line tasks based on resource capability values ​​provided in an embodiment of the present invention preliminarily screens all resources in a resource database according to the capability values ​​corresponding to each task requirement dimension in the capability value requirement list of the target task, thereby ensuring that the capability value of each resource in each task requirement dimension meets the requirements of the target task, and then screens again based on non-capability value conditions, and finally determines multiple candidate resources, so that the resources obtained from the two screenings are more in line with the requirements of the target task, which helps to achieve accurate and efficient task scheduling.

[0035] In an optional implementation, based on multiple task requirement dimensions in the capability value requirement list of the target task, multiple intermediate resources are screened from a resource database, including:

[0036] For each task requirement dimension in the capability value requirement list of the target task, determine the capability assessment dimension corresponding to the task requirement dimension;

[0037] For any resource in the resource database, determine the capability value of the resource under the capability assessment dimension corresponding to the task requirement dimension, and determine it as a candidate capability value;

[0038] Determine whether the candidate capability value is greater than the target capability value corresponding to the task requirement dimension;

[0039] When the candidate capability values ​​corresponding to each task requirement dimension are greater than the target capability value, the resource is regarded as an intermediate resource.

[0040] The production line task scheduling method based on resource capability value provided by the embodiment of the present invention clarifies the capability evaluation dimension corresponding to each task requirement dimension, thereby screening intermediate resources based on the relationship between the capability value of the task requirement dimension and the candidate capability value under the corresponding capability evaluation dimension, ensuring that the screened intermediate resources have sufficient capabilities in all aspects, thereby providing a high-quality foundation for finally determining the candidate resources.

[0041] In an optional implementation, determining a target resource based on historical tasks and multiple candidate resources includes:

[0042] Based on the similarity between each historical task and the target task, a plurality of target historical tasks are determined;

[0043] Obtain multiple historical resources assigned to each target historical task and a score of each historical resource;

[0044] Based on the score of each historical resource and the multiple candidate resources, a target resource is determined from the multiple historical resources and the multiple candidate resources.

[0045] The production line task scheduling method based on resource capability values ​​provided in an embodiment of the present invention calculates the similarity between historical tasks and target tasks, screens target historical tasks with high similarity, and then obtains multiple historical resources allocated to each target historical task and the score of each historical resource. By collecting and analyzing the scores of historical resources, the historical performance of each resource can be fully understood, and combined with the candidate resources screened based on the capability values, data support is provided for the subsequent determination of target resources.

[0046] In an optional implementation, based on the score of each historical resource and the multiple candidate resources, determining the target resource from the multiple historical resources and the multiple candidate resources includes:

[0047] When the score of any historical resource is greater than a first preset score threshold, the historical resource with the highest score is determined as the target resource;

[0048] When the scores of all historical resources are less than the second preset score threshold, the candidate resource with the highest capability value is used as the target resource.

[0049] The production line task scheduling method based on resource capability values ​​provided in an embodiment of the present invention ensures that the selected target resources are either historical resources with good historical performance or candidate resources that are highly consistent with the requirements of the target tasks through the scoring of historical resources and the capability values ​​of candidate resources, thereby achieving efficient and accurate task scheduling.

[0050] In a second aspect, the present invention provides a production line task scheduling device based on resource capability values, the device comprising:

[0051] An acquisition module, used to obtain the capability value requirement list of the target task and the resource characteristics of all resources in the task scheduling software;

[0052] An evaluation module is used to evaluate the capacity of each resource based on the resource characteristics of the resource using a resource capacity model, obtain the capacity value of the resource under multiple capacity evaluation dimensions, and store it in the resource database of the task scheduling software. The capacity value is used to measure the productivity of the resource under any capacity evaluation dimension;

[0053] A screening module, used to screen multiple candidate resources that meet the capability value requirement list of the target task from the resource database;

[0054] A determination module, used to determine target resources based on historical tasks and multiple candidate resources;

[0055] The scheduling module is used to allocate target resources to target tasks.

[0056] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the production line task scheduling method based on resource capability value of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0057] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the production line task scheduling method based on resource capability values ​​of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 is a flowchart of a production line task scheduling method based on resource capability values ​​according to an embodiment of the present invention;

[0060] Figure 2 is a structural block diagram of a production line task scheduling device based on resource capability values ​​according to an embodiment of the present invention;

[0061] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0063] The existing task scheduling has the problem of "resource islands", which reduces production efficiency and resource utilization, and cannot be applied to complex and changeable production line scenarios. The production line task scheduling method based on resource capability values ​​provided in the embodiment of the present invention uses a resource capability model to perform multi-dimensional capability evaluation on each resource, quantifies the productivity of resources, and refers to the data of historical tasks to jointly determine the target resources, and schedule the target resources to the target tasks, thereby improving resource utilization and production efficiency, optimizing resource allocation, and being able to adapt to complex and changeable production line scenarios.

[0064] According to an embodiment of the present invention, an embodiment of a production line task scheduling method based on resource capability values ​​is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0065] In this embodiment, a production line task scheduling method based on resource capability value is provided, which can be used in a terminal in which task scheduling software is installed. Figure 1 is a flowchart of a production line task scheduling method based on resource capability values ​​according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0066] Step S101, obtaining a capability requirement list of a target task and resource characteristics of all resources in the task scheduling software.

[0067] Specifically, the task scheduling software is used to allocate the resources on the production line to the target task according to the capability value requirement list of the target task. Among them, the resource is a plurality of lathes on the production line; the target task is the production process; the capability value requirement list is the requirement of the target task for the required resources, so as to allocate the resources that meet the requirements to the target task; the resource characteristics include test data, historical performance data, etc. Test data refers to the data obtained by testing the resource before the resource is put into the production line, such as load status, performance attributes, etc., and historical performance data refers to the performance attribute data of the resource when executing historical tasks.

[0068] Step S102: For each resource, a resource capability model is used to perform capability assessment based on the resource characteristics of the resource, and the capability value of the resource under multiple capability assessment dimensions is obtained and stored in the resource database of the task scheduling software. The capability value is used to measure the productivity of the resource under any capability assessment dimension.

[0069] Specifically, the capability assessment dimension refines the resource characteristics of the resource into multiple dimensions, such as diameter tolerance dimension, surface roughness dimension, groove width dimension, groove depth dimension, groove type tolerance dimension, etc. The resource capability model can determine the productivity of the resource under each capability assessment dimension, that is, the capability value. The resource database stores the capability values ​​of all resources in the task scheduling software. After the capability value of a resource is determined using the resource capability model, the resource is stored in the resource database together with its capability value under each capability assessment dimension, providing a data basis for task scheduling.

[0070] Step S103, screening multiple candidate resources that meet the capability value requirement list of the target task from the resource database.

[0071] Specifically, the capability value requirement list of the target task lists the productivity that the resources required for the current process should have in multiple dimensions. By comparing the resources in the resource database with the list, all candidate resources that meet the list can be screened out, which helps to schedule tasks efficiently and accurately.

[0072] Step S104: determining a target resource based on historical tasks and multiple candidate resources.

[0073] Specifically, the historical task is the completed process on the production line. The completed process can provide a scheduling reference for the current target process, and the most suitable target resource can be selected by combining the candidate resources determined based on the capability value, comprehensively considering the historical performance and the actual productivity of the resource.

[0074] Step S105: Allocate target resources to target tasks.

[0075] Specifically, the task scheduling software allocates target resources to target tasks so that the selected lathe can execute the target process. Compared with the existing scheduling method of allocating idle lathes to processes, it can schedule tasks according to the actual productivity of the lathe, improve resource utilization and production efficiency of the production line, and can adapt to complex production line scenarios.

[0076] The production line task scheduling method based on resource capability values ​​provided in the embodiment of the present invention obtains the capability value requirement list of the target task to understand the requirements of the target task. At the same time, it collects the resource characteristics of all resources in the task scheduling software, which helps to fully grasp the situation of available resources, and uses the resource capability model to perform multi-dimensional capability evaluation on each resource, quantify the productivity of the resources, and provide data support for subsequent task scheduling. By comparing with the requirement list of the target task, it can quickly locate qualified candidate resources, improve task scheduling efficiency, comprehensively determine the target resources based on historical tasks and candidate resources, and schedule the target resources to the target task. Compared with task scheduling based on whether the resources are idle, it improves resource utilization and production efficiency, optimizes resource allocation, and can adapt to complex and changeable production line scenarios.

[0077] In this embodiment, a production line task scheduling method based on resource capability value is provided, which can be used for the above-mentioned terminal. The method specifically includes the following steps:

[0078] Step S201, obtaining a capability requirement list of a target task and resource characteristics of all resources in the task scheduling software.

[0079] Specifically, the above step S201 obtains the capability value requirement list of the target task, including:

[0080] Step S2011, dividing the task requirement into multiple dimensions based on the target task.

[0081] Specifically, the task requirement dimension is used to describe multiple process requirements of the resources needed to complete the target task. For example, if the target task is a drilling process, the corresponding task requirement dimensions are the hole diameter tolerance dimension, the hole depth tolerance dimension, and the strength dimension; if the target task is an external cylindrical rough turning process, the corresponding task requirement dimensions are the diameter tolerance dimension and the surface roughness dimension; if the target task is a grooving process, the corresponding task requirement dimensions are the groove width dimension, the groove depth dimension, and the groove type tolerance dimension. Optionally, the task requirement dimensions corresponding to the target task are generally pre-set. The above are only examples and are not intended to be limiting. Production personnel can adjust them according to actual needs.

[0082] Step S2012, determining the capability value corresponding to each task requirement dimension.

[0083] Specifically, the capability value corresponding to each task requirement dimension is used to represent the standard that the resource's process requirements should meet, and is set by production personnel based on actual production conditions. If the target task is a drilling process, the corresponding task requirement dimensions and their capability values ​​are aperture tolerance dimension: standard aperture tolerance ±0.05mm, hole depth tolerance dimension: standard hole depth tolerance ±0.2mm, and strength dimension: 300Mpa.

[0084] Step S2013, generating a capability value requirement list for the target task based on the non-capability value conditions of the target task, all task requirement dimensions and the capability value corresponding to each task requirement dimension.

[0085] Specifically, the requirements of the target tasks include the task requirement dimensions expressed by capability values, and also include non-capability value conditions that cannot be expressed by capability values, such as geographic location, cost, etc., and the two are combined to obtain a complete capability value requirement list. Optionally, the following Table 1 is a capability value requirement list for multiple target tasks of a batch of component processing production lines, which is only an example and is not intended to be limiting.

[0086] Table 1

[0087]

[0088]

[0089] Step S202: For each resource, a resource capability model is used to perform capability assessment based on the resource characteristics of the resource, and the capability value of the resource under multiple capability assessment dimensions is obtained and stored in the resource database of the task scheduling software. The capability value is used to measure the productivity of the resource under any capability assessment dimension. The resource characteristics include test data and historical performance data.

[0090] Specifically, the above step S202 includes:

[0091] Step S2021, based on the test data and historical performance data in the resource characteristics of each resource, divide all resources into known resources and unknown resources.

[0092] Specifically, there are multiple resources in the task scheduling software, but not all resources have been tested. There are differences in the way to determine the capability value for tested and untested resources, so the resources need to be divided. If the test data of a resource is empty, it means that it has not been tested. In particular, if the historical performance data of a resource is empty, it has not been put into the production line, that is, it has not participated in task scheduling, and at this time, the resource is also considered to be untested.

[0093] Step S2022: for any known resource, based on the resource characteristics of the known resource, the capability value of the known resource in multiple capability evaluation dimensions is determined using the empirical formula in the resource capability model.

[0094] In some optional implementations, the above step S2022 includes:

[0095] Step a1: for any capability assessment dimension, based on the resource characteristics of the known resources, determine the actual production capacity and test yield rate of the known resources in the capability assessment dimension.

[0096] Specifically, any resource, that is, any lathe, has an original value. For example, the label of lathe A is marked with a strength of 500Mpa, and this 500Mpa is the original value. When testing lathe A, the maximum strength obtained from the test is 450Mpa, and this 450Mpa is used as the extreme value of lathe A. Any value between the original value and the extreme value is used as the actual production capacity of the lathe under the strength dimension. The test yield rate refers to the proportion of the number of products that are judged to be qualified after quality inspection to the total number of processed products during the test process of product processing on a certain lathe.

[0097] Step a2, obtaining the health index, resource utilization and resource penalty value of the known resources, where the resource penalty value is used to reduce the scheduling of the known resources when the resource utilization of the known resources exceeds a preset threshold.

[0098] Specifically, the health index is used to evaluate the state of resources. The longer the lathe is used, the more negative situations such as wear and tear and failure may occur, and the smaller the health index. In the actual production process, the production personnel can manually check the lathe to determine the health index. The resource utilization rate is used to evaluate the use of resources. If lathe A can be used to produce 100 parts and it has produced 30 parts, it can be obtained that the resource utilization rate of lathe A is 30%. The resource penalty value is used to regulate the scheduling of resources. If the resource utilization rate of a lathe exceeds a preset threshold, such as 90%, a fatigue warning will be issued to the lathe, and the resource penalty value will be added when calculating the capacity value to reduce the capacity value of the resource, thereby reducing the scheduling of the lathe. Optionally, the preset threshold and resource penalty value can be set by the production personnel, and the embodiment of the present invention does not limit this.

[0099] Step a3, using an empirical formula, based on the actual production capacity, test yield, health index, resource utilization and resource penalty value of the known resources in the capability assessment dimension, determine the capability value of the known resources in the capability assessment dimension.

[0100] Specifically, based on the various data obtained in the above steps, the empirical formula is adopted: Capacity value = actual production capacity * health index * (1-resource utilization) * test yield rate - resource penalty value, which can obtain the capacity value of resources in any capacity evaluation dimension to accurately evaluate the productivity of resources and provide a basis for task scheduling.

[0101] Step S2023: For any unknown resource, a graph clustering model in the resource capability model is used to obtain the capability value of the unknown resource in each capability evaluation dimension, and the graph clustering model is obtained based on training of known resources.

[0102] In some optional implementations, the above step S2023 includes:

[0103] Step b1: Calculate the similarity between the unknown resource and each cluster in the graph clustering model based on the resource characteristics of the unknown resource.

[0104] Specifically, the ability values of the known resources can be calculated through the above empirical formula. A graph clustering model is trained based on the known resources so as to calculate the ability values of the unknown resources based on this graph clustering model. Optionally, in the embodiments of the present invention, the structure of an existing graph clustering model is adopted, and based on the ability values of the existing resources in multiple ability evaluation dimensions, the training method of the existing graph clustering model is used for training, and the training process will not be elaborated here. Input the resource characteristics of the unknown resource into the graph clustering model, and use a similarity measurement method, such as Euclidean distance, cosine similarity, Manhattan distance, etc., to calculate the similarity between the unknown resource and the cluster center of each cluster, and for each cluster, obtain a similarity.

[0105] Step b2: Determine the ability values of the unknown resource in multiple ability evaluation dimensions based on the ability values of all the known resources in the cluster with the maximum similarity in multiple ability evaluation dimensions.

[0106] Specifically, according to the similarity calculated in step b1, find the cluster with the maximum similarity. Obtain the ability values of all the known resources in this cluster in multiple ability evaluation dimensions, and use statistical methods or machine learning models, such as mean, weighted average, linear regression, etc., to aggregate the ability values of these known resources to estimate the ability values of the unknown resources. For example, the average value of the ability values of all the known resources in a certain ability evaluation dimension in this cluster can be taken as the estimated value of the unknown resource. Or, the ability value can be determined by weighted averaging according to the similarity between the unknown resource and each known resource in this cluster. By using the graph clustering model to determine the ability values of the unknown resources based on the ability values of the known resources, the evaluation of all resources in the task scheduling software is realized, providing a basis for task scheduling.

[0107] Step S203: Screen out multiple candidate resources from the resource database that meet the list of ability value requirements for the target task.

[0108] Specifically, the above step S203 includes:

[0109] Step S2031: Screen out multiple intermediate resources from the resource database based on multiple task requirement dimensions in the list of ability value requirements for the target task.

[0110] In some optional embodiments, the above step S2031 includes:

[0111] Step c1: For each task requirement dimension in the list of ability value requirements for the target task, determine the ability evaluation dimension corresponding to the task requirement dimension.

[0112] Specifically, for each task requirement dimension in the capability value requirement list of the target task, find the corresponding resource capability assessment dimension. For example, as shown in Table 1 above, if the target task requires a "slot depth dimension", the corresponding capability assessment dimension is the "slot depth dimension", thereby ensuring that the capability values ​​of the same dimension are compared in the subsequent screening process, thereby improving the accuracy of the screening.

[0113] Step c2: for any resource in the resource database, determine the capability value of the resource under the capability assessment dimension corresponding to the task requirement dimension, and determine it as a candidate capability value.

[0114] Specifically, for any resource, the capability value of each resource in the capability assessment dimension corresponding to the task requirement dimension required by the target task is obtained as a candidate capability value.

[0115] Step c3, determining whether the candidate capability value is greater than the target capability value corresponding to the task requirement dimension.

[0116] Specifically, if the candidate capability value is greater than the target capability value corresponding to the task requirement dimension, it is considered that the resource meets the requirement of the target task in the capability evaluation dimension corresponding to the candidate capability value.

[0117] Step c4: when the candidate capability values ​​corresponding to each task requirement dimension are greater than the target capability value, the resource is used as an intermediate resource.

[0118] Specifically, if any resource can meet the capability value requirements of all task demand dimensions of the target task, then the resource is considered to be able to perform the target task and is regarded as an intermediate resource.

[0119] Step S2032: determining a plurality of candidate resources from a plurality of intermediate resources based on the non-capability value conditions in the capability value requirement list.

[0120] Specifically, among the intermediate resources that have met the capability value requirements, other non-capability value conditions, such as cost, availability, and geographical location, are considered to further screen out the most suitable candidate resources. Assuming that the target task is any process in the factory production line located in location A, and the task scheduling software includes a large number of resources, the selected intermediate resources may not all be located in location A, and further screening is required based on geographical location. Alternatively, if the cost requirement of the target task is 200,000 yuan, and the cost of using any resource is 250,000 yuan, which exceeds the requirement of the target task, the resource cannot be scheduled to the target task. By comprehensively considering multiple factors, it is ensured that the candidate resources finally selected not only meet the requirements in terms of capability value, but also have advantages in other important aspects, thereby improving the feasibility of task scheduling.

[0121] Step S204: determining a target resource based on historical tasks and multiple candidate resources.

[0122] Specifically, the above step S204 includes:

[0123] Step S2041 : determining a plurality of target historical tasks based on the similarity between each historical task and the target task.

[0124] Specifically, the historical tasks are all the processes completed on the production line within the historical time period. The cosine similarity between each historical task and the target task is calculated. The closer the cosine similarity is to 1, the more similar it is. The cosine similarity is sorted from large to small, and a preset number of historical tasks in the front are determined as target historical tasks. These target historical tasks are most similar to the current target task, so that the experience and performance of resource scheduling in these target historical tasks can be used to schedule the current target task.

[0125] Step S2042: Acquire multiple historical resources allocated to each target historical task and the score of each historical resource.

[0126] Specifically, the resources used in the target historical tasks and their scores are collected. The score reflects the degree to which the resources meet the task requirements. After each task is completed, the production staff will score the resource capacity based on comprehensive factors such as the quality of task completion, consumables consumption, and duration. The maximum value of the score is 10.

[0127] Step S2043 : determining a target resource from the multiple historical resources and the multiple candidate resources based on the score of each historical resource and the multiple candidate resources.

[0128] In some optional implementations, the above step S2043 includes:

[0129] Step d1: when the score of any historical resource is greater than a first preset score threshold, the historical resource with the highest score is determined as the target resource.

[0130] Specifically, the value of the first preset scoring threshold should be relatively large, so that if the score of a historical resource is greater than the first preset scoring threshold, it means that the historical resource performs well in the target historical task and can be recommended to the target task for scheduling. If the scores of multiple historical resources are all greater than the first preset scoring threshold, the historical resource with the best performance, that is, the highest score, is determined as the target resource.

[0131] Step d2: When the scores of all historical resources are less than a second preset score threshold, the candidate resource with the highest capability value is selected as the target resource.

[0132] Specifically, the value of the first preset scoring threshold should be small, so that if the scores of all historical resources are less than the second preset scoring threshold, it means that all historical resources have poor performance in the target historical task and cannot be recommended for scheduling to the target task. At this time, the target resource is determined from the candidate resources. If there are multiple candidate resources, they are sorted from large to small according to the capability value under each capability evaluation dimension, and the candidate resource with the most number of rankings in the first place under all capability evaluation dimensions is determined as the target resource.

[0133] Step S205: Allocate the target resource to the target task. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0134] In some optional implementations, the task scheduling software will track the scheduling of each resource, and when the scheduling of any resource reaches a trigger condition, the capacity value will be re-determined according to the empirical formula and updated in the resource database. The trigger condition may be resource utilization exceeding a threshold, hardware failure, performance degradation, etc.

[0135] The production line task scheduling method based on resource capability values ​​provided in the embodiment of the present invention obtains the capability value requirement list of the target task to understand the requirements of the target task. At the same time, it collects the resource characteristics of all resources in the task scheduling software, which helps to fully grasp the situation of available resources, and uses the resource capability model to perform multi-dimensional capability evaluation on each resource, quantify the productivity of the resources, and provide data support for subsequent task scheduling. By comparing with the requirement list of the target task, it can quickly locate qualified candidate resources, improve task scheduling efficiency, comprehensively determine the target resources based on historical tasks and candidate resources, and schedule the target resources to the target task. Compared with task scheduling based on whether the resources are idle, it improves resource utilization and production efficiency, optimizes resource allocation, and can adapt to complex and changeable production line scenarios.

[0136] In this embodiment, a production line task scheduling device based on resource capability value is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0137] This embodiment provides a production line task scheduling device based on resource capacity values, such as Figure 2 As shown, including:

[0138] The acquisition module 201 is used to acquire the capability value requirement list of the target task and the resource characteristics of all resources in the task scheduling software.

[0139] The evaluation module 202 is used to perform capacity evaluation on each resource based on the resource characteristics of the resource using the resource capacity model, obtain the capacity value of the resource under multiple capacity evaluation dimensions, and store it in the resource database of the task scheduling software. The capacity value is used to measure the productivity of the resource under any capacity evaluation dimension.

[0140] The screening module 203 is used to screen multiple candidate resources that meet the capability value requirement list of the target task from the resource database.

[0141] The determination module 204 is used to determine the target resource based on the historical tasks and multiple candidate resources.

[0142] The scheduling module 205 is used to allocate target resources to target tasks.

[0143] In some optional implementations, the resource characteristics include test data and historical performance data.

[0144] The evaluation module 202 includes:

[0145] The first division unit is used to divide all resources into known resources and unknown resources based on the test data and historical performance data in the resource characteristics of each resource.

[0146] The first determination unit is used to determine the capability value of any known resource in multiple capability evaluation dimensions based on the resource characteristics of the known resource and using the empirical formula in the resource capability model.

[0147] The second determination unit is used to obtain the capability value of the unknown resource in each capability evaluation dimension by using the graph clustering model in the resource capability model for any unknown resource, wherein the graph clustering model is obtained by training based on known resources.

[0148] In some optional implementations, the first determining unit includes:

[0149] The first determination subunit is used to determine, for any capability assessment dimension, the actual production capacity and test yield rate of the known resources in the capability assessment dimension based on the resource characteristics of the known resources.

[0150] The acquisition subunit is used to obtain the health index, resource utilization and resource penalty value of the known resources. The resource penalty value is used to reduce the scheduling of the known resources when the resource utilization of the known resources exceeds a preset threshold.

[0151] The second determination subunit is used to determine the capability value of the known resource in the capability assessment dimension by using an empirical formula based on the actual production capacity, test yield, health index, resource utilization rate and resource penalty value of the known resource in the capability assessment dimension.

[0152] In some optional implementations, the second determining unit includes:

[0153] The calculation subunit is used to calculate the similarity between the unknown resource and each cluster in the graph clustering model based on the resource characteristics of the unknown resource.

[0154] The third determination subunit is used to determine the capability values ​​of the unknown resource in multiple capability evaluation dimensions based on the capability values ​​of all known resources in the cluster with the greatest similarity in multiple capability evaluation dimensions.

[0155] In some optional implementations, the acquisition module 201 includes:

[0156] The second division unit is used to divide the task requirement dimensions based on the target task.

[0157] The first determining unit is used to determine the capability value corresponding to each task requirement dimension.

[0158] The generating unit is used to generate a capability value requirement list for the target task based on the non-capability value conditions of the target task, all task requirement dimensions and the capability value corresponding to each task requirement dimension.

[0159] In some optional implementations, the screening module 203 includes:

[0160] The first screening unit is used to screen and obtain multiple intermediate resources from a resource database based on multiple task requirement dimensions in the capability value requirement list of the target task.

[0161] The second determining unit is used to determine a plurality of candidate resources from a plurality of intermediate resources based on the non-capability value conditions in the capability value requirement list.

[0162] In some optional embodiments, the first screening unit includes:

[0163] The fourth determining subunit is used to determine, for each task requirement dimension in the capability value requirement list of the target task, a capability assessment dimension corresponding to the task requirement dimension.

[0164] The fifth determination subunit is used to determine, for any resource in the resource database, a capability value of the resource under the capability evaluation dimension corresponding to the task requirement dimension, and determine it as a candidate capability value.

[0165] The judgment subunit is used to judge whether the candidate capability value is greater than the target capability value corresponding to the task requirement dimension.

[0166] The sixth determination subunit is used to use the resource as an intermediate resource when the candidate capability values ​​corresponding to each task requirement dimension are greater than the target capability value.

[0167] In some optional implementations, the determination module 204 includes:

[0168] The third determining unit is used to determine a plurality of target historical tasks based on the similarity between each historical task and the target task.

[0169] The acquisition unit is used to acquire multiple historical resources allocated to each target historical task and the score of each historical resource.

[0170] The fourth determining unit is configured to determine a target resource from among the multiple historical resources and the multiple candidate resources based on the score of each historical resource and the multiple candidate resources.

[0171] In some optional implementations, the fourth determining unit includes:

[0172] The seventh determination subunit is configured to determine the historical resource with the highest score as the target resource when the score of any historical resource is greater than a first preset score threshold.

[0173] The eighth determination subunit is configured to select the candidate resource with the highest capability value as the target resource when the scores of all historical resources are less than a second preset score threshold.

[0174] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0175] The resource capability value-based production line task scheduling device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0176] The embodiment of the present invention also provides a computer device having the above Figure 2 The production line task scheduling device based on resource capability value is shown.

[0177] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0178] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0179] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0180] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0181] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0182] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0183] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0184] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0185] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0186] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A production line task scheduling method based on resource capability value, characterized in that: The method comprises: Obtain the capability value requirement list of the target task and the resource characteristics of all resources in the task scheduling software; For each resource, a resource capability model is used to perform capability evaluation based on the resource characteristics of the resource, and capability values ​​of the resource under multiple capability evaluation dimensions are obtained and stored in the resource database of the task scheduling software. The capability values ​​are used to measure the productivity of the resource under any capability evaluation dimension. Screening multiple candidate resources from the resource database that meet the capability value requirement list of the target task; Determine a target resource based on the historical tasks and the plurality of candidate resources; The target resource is allocated to the target task.

2. The method according to claim 1, characterized in that The resource characteristics include test data and historical performance data; For each resource, a resource capability model is used to perform capability evaluation based on the resource characteristics of the resource to obtain capability values ​​of the resource under multiple capability evaluation dimensions, including: Based on the test data and historical performance data in the resource characteristics of each resource, all resources are divided into known resources and unknown resources; For any known resource, based on the resource characteristics of the known resource, using the empirical formula in the resource capability model, determine the capability value of the known resource in the multiple capability evaluation dimensions; For any unknown resource, a graph clustering model in a resource capability model is used to obtain the capability value of the unknown resource in each capability evaluation dimension, and the graph clustering model is trained based on the known resources.

3. The method according to claim 2, characterized in that For any known resource, based on the resource characteristics of the known resource, using the empirical formula in the resource capability model to determine the capability value of the known resource in the multiple capability evaluation dimensions includes: For any capability assessment dimension, based on the resource characteristics of the known resources, determine the actual production capacity and test yield rate of the known resources in the capability assessment dimension; Acquire a health index, a resource utilization rate, and a resource penalty value of the known resource, wherein the resource penalty value is used to reduce scheduling of the known resource when the resource utilization rate of the known resource exceeds a preset threshold; An empirical formula is used to determine the capability value of the known resource in the capability assessment dimension based on the actual production capacity, test yield, health index, resource utilization rate and resource penalty value of the known resource in the capability assessment dimension.

4. The method according to claim 2, characterized in that: For any unknown resource, the graph clustering model in the resource capability model is used to obtain the capability value of the unknown resource in each capability evaluation dimension, including: Based on the resource characteristics of the unknown resource, calculating the similarity between the unknown resource and each cluster in the graph clustering model; Based on the capability values ​​of all known resources in the cluster with the greatest similarity in the multiple capability evaluation dimensions, the capability values ​​of the unknown resource in the multiple capability evaluation dimensions are determined.

5. The method according to claim 1, characterized in that The capability value requirement list for obtaining the target task includes: Based on the target task, divide the task requirement into multiple dimensions; Determine the capability value corresponding to each task requirement dimension; Based on the non-capability value conditions of the target task, all task requirement dimensions and the capability value corresponding to each task requirement dimension, a capability value requirement list of the target task is generated.

6. The method according to claim 5, characterized in that The step of screening a plurality of candidate resources from the resource database that meet the capability value requirement list of the target task includes: Based on the multiple task requirement dimensions in the capability value requirement list of the target task, multiple intermediate resources are screened from the resource database; The plurality of candidate resources are determined from the plurality of intermediate resources based on the non-capability value conditions in the capability value requirement list.

7. The method according to claim 6, characterized in that The multiple task requirement dimensions in the capability value requirement list of the target task are screened from the resource database to obtain multiple intermediate resources, including: For each task requirement dimension in the capability value requirement list of the target task, determining the capability assessment dimension corresponding to the task requirement dimension; For any resource in the resource database, determining a capability value of the resource under the capability assessment dimension corresponding to the task requirement dimension, and determining the capability value as a candidate capability value; Determine whether the candidate capability value is greater than the target capability value corresponding to the task requirement dimension; When the candidate capability values ​​corresponding to each task requirement dimension are greater than the target capability value, the resource is used as the intermediate resource.

8. The method according to claim 1, characterized in that The determining of the target resource based on the historical tasks and the plurality of candidate resources includes: Determining a plurality of target historical tasks based on the similarity between each historical task and the target task; Obtain multiple historical resources assigned to each target historical task and a score of each historical resource; The target resource is determined from the multiple historical resources and the multiple candidate resources based on the score of each historical resource and the multiple candidate resources.

9. The method according to claim 8, characterized in that The step of determining the target resource from the multiple historical resources and the multiple candidate resources based on the score of each historical resource and the multiple candidate resources comprises: When the score of any historical resource is greater than a first preset score threshold, the historical resource with the highest score is determined as the target resource; When the scores of all historical resources are less than the second preset score threshold, the candidate resource with the highest capability value is used as the target resource.

10. A production line task scheduling device based on resource capability value, characterized in that: The device comprises: An acquisition module, used to obtain the capability value requirement list of the target task and the resource characteristics of all resources in the task scheduling software; An evaluation module, for evaluating the capacity of each resource by using a resource capacity model based on the resource characteristics of the resource, obtaining the capacity value of the resource under multiple capacity evaluation dimensions, and storing the capacity value in the resource database of the task scheduling software, wherein the capacity value is used to measure the productivity of the resource under any capacity evaluation dimension; A screening module, used to screen multiple candidate resources that meet the capability value requirement list of the target task from the resource database; A determination module, configured to determine a target resource based on the historical tasks and the plurality of candidate resources; A scheduling module is used to allocate the target resource to the target task.

Images